[iceberg] branch master updated: Core: Fix unicode handling in HTTPClient (#8046)

[dweeks]

This is an automated email from the ASF dual-hosted git repository.

dweeks pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/iceberg.git


The following commit(s) were added to refs/heads/master by this push:
     new 9572585779 Core: Fix unicode handling in HTTPClient (#8046)
9572585779 is described below

commit 95725857791333f4fa8a8db6d37472cd457cb9f9
Author: Eduard Tudenhoefner <etudenhoef...@gmail.com>
AuthorDate: Thu Jul 13 19:41:07 2023 +0200

    Core: Fix unicode handling in HTTPClient (#8046)
    
    fixes #7821
    
    Without the fix, tests would fail with
    ```
    expected: struct<1: id: required int (unique ID 🤪), 2: data: required 
string>
     but was: struct<1: id: required int (unique ID ?), 2: data: required 
string>
    ```
---
 core/src/main/java/org/apache/iceberg/rest/HTTPClient.java      | 7 ++++---
 core/src/test/java/org/apache/iceberg/catalog/CatalogTests.java | 6 +++---
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/core/src/main/java/org/apache/iceberg/rest/HTTPClient.java 
b/core/src/main/java/org/apache/iceberg/rest/HTTPClient.java
index 9af4b56797..b2b6fc8a7c 100644
--- a/core/src/main/java/org/apache/iceberg/rest/HTTPClient.java
+++ b/core/src/main/java/org/apache/iceberg/rest/HTTPClient.java
@@ -24,6 +24,7 @@ import java.io.IOException;
 import java.io.UncheckedIOException;
 import java.net.URI;
 import java.net.URISyntaxException;
+import java.nio.charset.StandardCharsets;
 import java.util.Map;
 import java.util.function.Consumer;
 import java.util.stream.Collectors;
@@ -105,7 +106,7 @@ public class HTTPClient implements RESTClient {
       }
 
       // EntityUtils.toString returns null when HttpEntity.getContent returns 
null.
-      return EntityUtils.toString(response.getEntity(), "UTF-8");
+      return EntityUtils.toString(response.getEntity(), 
StandardCharsets.UTF_8);
     } catch (IOException | ParseException e) {
       throw new RESTException(e, "Failed to convert HTTP response body to 
string");
     }
@@ -471,13 +472,13 @@ public class HTTPClient implements RESTClient {
 
   private StringEntity toJson(Object requestBody) {
     try {
-      return new StringEntity(mapper.writeValueAsString(requestBody));
+      return new StringEntity(mapper.writeValueAsString(requestBody), 
StandardCharsets.UTF_8);
     } catch (JsonProcessingException e) {
       throw new RESTException(e, "Failed to write request body: %s", 
requestBody);
     }
   }
 
   private StringEntity toFormEncoding(Map<?, ?> formData) {
-    return new StringEntity(RESTUtil.encodeFormData(formData));
+    return new StringEntity(RESTUtil.encodeFormData(formData), 
StandardCharsets.UTF_8);
   }
 }
diff --git a/core/src/test/java/org/apache/iceberg/catalog/CatalogTests.java 
b/core/src/test/java/org/apache/iceberg/catalog/CatalogTests.java
index 5641dce89f..203b5fc381 100644
--- a/core/src/test/java/org/apache/iceberg/catalog/CatalogTests.java
+++ b/core/src/test/java/org/apache/iceberg/catalog/CatalogTests.java
@@ -74,19 +74,19 @@ public abstract class CatalogTests<C extends Catalog & 
SupportsNamespaces> {
   // Schema passed to create tables
   protected static final Schema SCHEMA =
       new Schema(
-          required(3, "id", Types.IntegerType.get(), "unique ID"),
+          required(3, "id", Types.IntegerType.get(), "unique ID 🤪"),
           required(4, "data", Types.StringType.get()));
 
   // This is the actual schema for the table, with column IDs reassigned
   private static final Schema TABLE_SCHEMA =
       new Schema(
-          required(1, "id", Types.IntegerType.get(), "unique ID"),
+          required(1, "id", Types.IntegerType.get(), "unique ID 🤪"),
           required(2, "data", Types.StringType.get()));
 
   // This is the actual schema for the table, with column IDs reassigned
   private static final Schema REPLACE_SCHEMA =
       new Schema(
-          required(2, "id", Types.IntegerType.get(), "unique ID"),
+          required(2, "id", Types.IntegerType.get(), "unique ID 🤪"),
           required(3, "data", Types.StringType.get()));
 
   // another schema that is not the same